CN109214637B - Network element power consumption determination method and device, storage medium and computing equipment - Google Patents
Network element power consumption determination method and device, storage medium and computing equipment Download PDFInfo
- Publication number
- CN109214637B CN109214637B CN201710552179.5A CN201710552179A CN109214637B CN 109214637 B CN109214637 B CN 109214637B CN 201710552179 A CN201710552179 A CN 201710552179A CN 109214637 B CN109214637 B CN 109214637B
- Authority
- CN
- China
- Prior art keywords
- power consumption
- time period
- network element
- data
- dimension
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000012549 training Methods 0.000 claims abstract description 27
- 238000012353 t test Methods 0.000 claims description 16
- 230000006870 function Effects 0.000 claims description 14
- 238000012847 principal component analysis method Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 13
- 238000001914 filtration Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 8
- 230000001419 dependent effect Effects 0.000 claims description 8
- 238000010586 diagram Methods 0.000 description 11
- 238000012986 modification Methods 0.000 description 5
- 230000004048 modification Effects 0.000 description 5
- 238000000692 Student's t-test Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000010295 mobile communication Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 239000006185 dispersion Substances 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides a method, a device, a storage medium and a computing device for determining power consumption of a network element, wherein the method comprises the following steps: determining theoretical power consumption of the first network element in a first time period by using a power consumption model obtained by pre-training according to power consumption influence data of the first network element in a specified area in the first time period; and determining the lowest power consumption and the highest power consumption of the first network element in the first time period according to the theoretical power consumption and the stored standard deviation of the historical power consumption of all the second network elements in the specified area in the second time period, wherein the second network elements are provided with intelligent electric meters. The method and the device can determine the power consumption range of the network element without the intelligent electric meter in a certain time period without manual participation.
Description
Technical Field
The present invention relates to the field of communications technologies, and in particular, to a method and an apparatus for determining power consumption of a network element, a storage medium, and a computing device.
Background
The electric charge accounts for a high proportion of the network operation and maintenance cost of the telecommunication operators, and the control of the electric charge is always the most troublesome problem for the telecommunication operators. The more the power consumption of the network element in the mobile communication network of the telecommunication operator is, the more the telecommunication operator needs to pay the electric charge, wherein the network element includes power consumption equipment such as a base station and a resource point.
At present, the means for collecting the power consumption of the network element mainly include the following two ways:
the method comprises the following steps of firstly, manually polling and reading meter, namely manually polling and checking each network element ammeter in a mobile communication network to obtain the power consumption of the network element;
and in the second mode, the intelligent electric meter is installed on the network element side, the intelligent electric meter collects the electric meter reading and transmits the electric meter reading to the server side in a remote transmission mode, and the telecommunication network operator obtains the power consumption of the network element from the server side.
However, the above two approaches have the following drawbacks, respectively: in the first mode, because manual participation is involved, the collection of the power consumption is greatly influenced by human factors, and the phenomenon of meter reading cannot be avoided, namely the phenomenon that the power consumption reported manually is larger than the actual power consumption of a network element; in the second mode, the smart meters need to be installed, but the number of network elements in the mobile communication network is large, the cost of the smart meters is too high, and the cost is greatly increased when the smart meters need to be installed in all the network elements.
Disclosure of Invention
The invention provides a method, a device, a storage medium and a computing device for determining power consumption of network elements, which are used for determining the power consumption of the network elements without manual participation and installation of intelligent electric meters on all the network elements, so that the cost of telecommunication network operators is reduced.
In a first aspect, an embodiment of the present invention provides a method for determining power consumption of a network element, where the method includes:
determining theoretical power consumption of the first network element in a first time period by using a power consumption model obtained by pre-training according to power consumption influence data of the first network element in a specified area in the first time period;
and determining the lowest power consumption and the highest power consumption of the first network element in the first time period according to the theoretical power consumption and the stored standard deviation of the historical power consumption of all the second network elements in the specified area in the second time period, wherein the second network elements are provided with intelligent electric meters.
Optionally, in the method, the power consumption model is obtained by training in the following manner:
acquiring N-dimensional power consumption influence historical data of each second network element in a second time period;
filtering distortion data in the acquired power consumption influence historical data to obtain N-dimension filtered power consumption influence historical data of each second network element;
for each second network element, performing dimensionality reduction on the filtered N-dimensional power consumption influence historical data of the second network element by using a principal component analysis method to obtain M-dimensional principal component data corresponding to the second network element, wherein N is an integer greater than 1, M is an integer greater than zero, and M is smaller than N;
and taking the M-dimension principal component data corresponding to each second network element as an independent variable, taking the power consumption of the corresponding second network element in a second time period as a dependent variable, and performing power consumption function fitting to obtain the power consumption model.
Optionally, in the method, filtering distortion data in the acquired power consumption influence history data specifically includes:
dividing the second time period into a plurality of sub-time periods according to a set step length;
for each dimension in the N dimensions, carrying out a variance homogeneity test on the dimension power consumption influence historical data in each sub-time period and the dimension power consumption influence historical data in a second time period;
and determining the dimension power consumption influence historical data in the sub-time period with the variance different from that of the dimension power consumption influence historical data in the second time period as distortion data, and discarding the distortion data.
Optionally, the method further comprises:
aiming at the dimension power consumption influence historical data in each sub-time period with the same variance as the dimension power consumption influence historical data in a second time period, carrying out single-population t test on the dimension power consumption influence historical data in the sub-time period and the dimension power consumption influence historical data in the second time period;
and if the single-population t test result is not in the preset range, determining the dimension power consumption influence historical data in the sub-time period as distortion data, and discarding the distortion data.
Optionally, in the method, if the power consumption influence data of the first network element in the first time period is N-dimensional power consumption influence data, determining the theoretical power consumption of the first network element in the first time period specifically includes:
performing dimensionality reduction processing on N-dimensional power consumption influence data of a first network element in a first time period by using the principal component analysis method to obtain M-dimensional principal component data corresponding to the first network element;
inputting M-dimension principal component data corresponding to the first network element into the power consumption model to obtain the output of the power consumption model;
and determining the output of the power consumption model as the theoretical power consumption of the first network element in the first time period.
Optionally, in the method, determining the lowest power consumption and the highest power consumption of the first network element in the first time period specifically includes:
determining the product of the standard deviation and a preset constant;
taking an absolute value of a difference value between the theoretical power consumption and the product as a lowest power consumption of the first network element in the first time period;
and taking the sum of the theoretical power consumption and the product as the highest power consumption of the first network element in the first time period.
In a second aspect, an embodiment of the present invention provides an apparatus for determining power consumption of a network element, including:
a first determining module, configured to determine, according to power consumption influence data of the first network element in a specified area in a first time period, theoretical power consumption of the first network element in the first time period by using a power consumption model obtained through pre-training;
and a second determining module, configured to determine, according to the theoretical power consumption and a standard deviation of stored historical power consumption of all second network elements in the specified area in a second time period, a lowest power consumption and a highest power consumption of the first network element in the first time period, where a smart meter is arranged on the second network element.
Optionally, the apparatus further comprises:
the training module is used for training to obtain the power consumption model in the following way:
acquiring N-dimensional power consumption influence historical data of each second network element in a second time period;
filtering distortion data in the acquired power consumption influence historical data to obtain N-dimension filtered power consumption influence historical data of each second network element;
for each second network element, performing dimensionality reduction on the filtered N-dimensional power consumption influence historical data of the second network element by using a principal component analysis method to obtain M-dimensional principal component data corresponding to the second network element, wherein N is an integer greater than 1, M is an integer greater than zero, and M is smaller than N;
and taking the M-dimension principal component data corresponding to each second network element as an independent variable, taking the power consumption of the corresponding second network element in a second time period as a dependent variable, and performing power consumption function fitting to obtain the power consumption model.
Optionally, in the apparatus, the training module is specifically configured to filter distortion data in the acquired power consumption impact history data in the following manner:
dividing the second time period into a plurality of sub-time periods according to a set step length;
for each dimension in the N dimensions, carrying out a variance homogeneity test on the dimension power consumption influence historical data in each sub-time period and the dimension power consumption influence historical data in a second time period;
and determining the dimension power consumption influence historical data in the sub-time period with the variance different from that of the dimension power consumption influence historical data in the second time period as distortion data, and discarding the distortion data.
Optionally, in the apparatus, the training module is further configured to:
aiming at the dimension power consumption influence historical data in each sub-time period with the same variance as the dimension power consumption influence historical data in a second time period, carrying out single-population t test on the dimension power consumption influence historical data in the sub-time period and the dimension power consumption influence historical data in the second time period;
and if the single-population t test result is not in the preset range, determining the dimension power consumption influence historical data in the sub-time period as distortion data, and discarding the distortion data.
Optionally, in the apparatus, if the power consumption impact data of the first network element in the first time period is N-dimensional power consumption impact data, the first determining module is specifically configured to:
performing dimensionality reduction processing on N-dimensional power consumption influence data of a first network element in a first time period by using the principal component analysis method to obtain M-dimensional principal component data corresponding to the first network element;
inputting M-dimension principal component data corresponding to the first network element into the power consumption model to obtain the output of the power consumption model;
and determining the output of the power consumption model as the theoretical power consumption of the first network element in the first time period.
Optionally, in the apparatus, the second determining module is specifically configured to:
determining the product of the standard deviation and a preset constant;
taking an absolute value of a difference value between the theoretical power consumption and the product as a lowest power consumption of the first network element in the first time period;
and taking the sum of the theoretical power consumption and the product as the highest power consumption of the first network element in the first time period.
In a third aspect, an embodiment of the present invention provides a non-volatile computer storage medium, where the computer storage medium stores an executable program, and the executable program is executed by a processor to implement any of the steps of the method for determining power consumption of a network element.
In a third aspect, an embodiment of the present invention provides a computing device, which includes a memory, a processor, and a computer program stored in the memory, where the processor implements the steps of any one of the above methods for determining power consumption of a network element when executing the program.
The method, the device, the storage medium and the computing equipment for determining the power consumption of the network element provided by the embodiment of the invention have the following beneficial effects:
the theoretical power consumption of the network element is determined by using the power consumption model obtained by pre-training and the power consumption influence data of the first network element, and the highest power consumption and the lowest power consumption of the first network element in a certain time period are determined according to the theoretical power consumption and the historical power consumption of the second network element provided with the intelligent electric meter, so that the power consumption range of the network element not provided with the intelligent electric meter in the certain time period can be determined without manual participation.
Drawings
The above and other objects, features and advantages of exemplary embodiments of the present invention will become readily apparent from the following detailed description read in conjunction with the accompanying drawings. Several embodiments of the invention are illustrated by way of example, and not by way of limitation, in the figures of the accompanying drawings and in which:
fig. 1 is a flowchart illustrating a method for determining power consumption of a network element according to an embodiment of the present invention;
fig. 2 is a flowchart illustrating a method for determining a lowest power consumption amount and a highest power consumption amount of a first network element in a first time period according to an embodiment of the present invention;
fig. 3 is a schematic flow chart of a method for training a power consumption model according to an embodiment of the present invention;
fig. 4 is a flowchart illustrating a method for filtering distortion data in acquired historical data of power consumption impact according to an embodiment of the present invention;
fig. 5 is a flowchart illustrating another method for filtering distortion data in acquired historical data of power consumption impact according to an embodiment of the present invention;
fig. 6 is a flowchart of a method for determining theoretical power consumption of a first network element in the first time period according to an embodiment of the present invention;
fig. 7 is a schematic structural diagram of a device for determining power consumption of a network element according to a second embodiment of the present invention;
fig. 8 is a schematic diagram of a hardware structure of a computing device according to a fourth embodiment of the present invention.
Detailed Description
The method, the apparatus, the storage medium, and the computing device for determining power consumption of a network element according to embodiments of the present invention are described in detail below with reference to specific embodiments.
Example one
As shown in fig. 1, a method for determining power consumption of a network element according to an embodiment of the present invention includes the following steps:
In a specific implementation, the designated area is a set geographic area, for example, the designated area may be beijing, or beijing plus district, and the size of the designated area may be set according to a requirement, which is not limited herein.
The first network element may be any one of network elements in the designated area, and preferably, the first network element is a network element in the designated area, which is not provided with the smart meter. The network element may be a base station, a resource point, an air conditioner, an exhaust fan, a lighting device, or other power consuming devices, or may be a machine room including a plurality of power consuming devices, and when the network element is the machine room, the total power consumption of all the power consuming devices in the whole machine room is determined by using the embodiment of the present invention.
The power consumption influence data of the first network element comprise dimensional data of actual power, rated power, no-load power, voltage value of the switching power supply, current value of the switching power supply, available time of the storage battery, temperature of the environment, humidity of the environment and the like of power consumption equipment included in the network element, and the size of the data can influence the power consumption of the network element.
The power consumption model obtained by pre-training is used to calculate the power consumption of the network element, and the training mode of the power consumption model will be described in detail below.
And step 102, determining the lowest power consumption and the highest power consumption of the first network element in the first time period according to the theoretical power consumption and the stored standard deviation of the historical power consumption of all the second network elements in the specified area in the second time period, wherein the second network elements are provided with smart meters.
The second network element is the network element provided with the intelligent electric meter, and the power consumption of the network element provided with the intelligent electric meter can be obtained through the intelligent electric meter. Preferably, the ending time point of the second time period is earlier than the starting time point of the first time period, of course, the second time period may also include the first time period, or the first time period includes the second time period, which is not limited herein.
In specific implementation, the standard deviation of the historical power consumption of all the second network elements in the specified area in the second time period is calculated and stored in advance, and the standard deviation calculation formula is as follows:
wherein σ is the standard deviation, N is the number of the second network elements, and xiAnd μ is an average value of the historical power consumption of the N network elements in the second time period, specifically, the historical power consumption of the network element i in the second time period.
In specific implementation, a smaller value of the standard deviation of the theoretical power consumption of the first network element in the first time period and the stored historical power consumption of all the second network elements in the specified area in the second time period is taken as a lowest power consumption of the first network element in the first time period, and a larger value of the standard deviation of the theoretical power consumption of the first network element in the first time period and the stored historical power consumption of all the second network elements in the specified area in the second time period is taken as a highest power consumption of the first network element in the first time period.
In a scene that a meter reader is required to report power consumption, after the meter reader reports the power consumption of the first network element in a first time period, whether the power consumption of the first network element reported by the meter reader in the first time period is accurate can be determined according to the determined highest power consumption and the determined lowest power consumption of the first network element in the first time period, if the power consumption of the first network element reported by the meter reader in the first time period is in a numerical range corresponding to the highest power consumption and the lowest power consumption, the power consumption of the first network element reported by the meter reader in the first time period is determined to be accurate, and otherwise, the power consumption of the first network element reported by the meter reader in the first time period is determined to be inaccurate.
In a scene that a meter reader is not required to report power consumption, a middle value of the highest power consumption and the lowest power consumption of the first network element in the first time period can be used as the power consumption of the first network element in the first time period.
It should be noted that both the power consumption impact data of the first network element and the historical power consumption of the second network element are collected and stored in advance.
According to the embodiment of the invention, the theoretical power consumption of the network element is determined by using the power consumption model obtained by pre-training and the power consumption influence data of the first network element, and the highest power consumption and the lowest power consumption of the first network element in a certain time period are determined according to the theoretical power consumption and the historical power consumption of the second network element provided with the intelligent electric meter, so that the power consumption range of the network element not provided with the intelligent electric meter in the certain time period can be determined without manual participation, and the power consumption range is used for determining the power consumption of the network element in the certain time period according to the actual application scene.
As a possible implementation, according to the content provided in fig. 2, the lowest power consumption and the highest power consumption of the first network element in the first time period are determined:
In specific implementation, the size of the preset constant may be set according to an actual application scenario, for example, the preset constant is 1.67, or may be other values, which is not limited herein. The execution sequence of step 202 and step 203 is not limited, or step 203 may be executed first and then step 202 is executed, or both steps may be executed simultaneously.
As a possible implementation, according to the content provided in fig. 3, the power consumption model is trained to be:
In specific implementation, the N-dimensional power consumption influence historical data of the second network element in the second time period and the historical power consumption of each second network element in the second time period are used for training sample data of the power consumption model. The N-dimensional power consumption influence history data is N-dimensional power consumption influence history data.
And step 302, filtering distortion data in the acquired power consumption influence historical data to obtain the N-dimensional filtered power consumption influence historical data of each second network element.
During specific implementation, data which is not accurate enough, namely distorted data, may exist in the stored power consumption influence history data of each second network element in the N dimension in the second time period, and the distorted data is filtered out in the step, so that the power consumption influence history data of each second network element after the N dimension is filtered is obtained, and the trained power consumption model is more accurate and reliable.
And step 303, performing dimensionality reduction on the filtered N-dimensional power consumption influence historical data of the second network element by using a principal component analysis method for each second network element to obtain M-dimensional principal component data corresponding to the second network element, wherein N is an integer larger than 1, M is an integer larger than zero, and M is smaller than N.
In specific implementation, firstly, the correlation among the filtered power consumption influence historical data of each dimension of the second network element is determined by using a Butterworth sphere test, and then, the filtered N-dimension power consumption influence historical data of the second network element is subjected to dimensionality reduction by using a principal component analysis method. Namely, the N-dimension power consumption influence history data is reduced to M-dimension main component data.
And step 304, performing power consumption function fitting by using the M-dimension principal component data corresponding to each second network element as an independent variable and the power consumption of the corresponding second network element in the second time period as a dependent variable to obtain the power consumption model.
In specific implementation, the power consumption model can be obtained by using an existing function fitting algorithm or tool, for example, by using a function fitting tool provided in matlab, the M-dimension principal component data corresponding to each second network element is used as an independent variable, the power consumption of the corresponding second network element in the second time period is used as a dependent variable, and the dependent variable is input into the tool, so that a power consumption calculation function can be obtained, the power consumption calculation function is the power consumption model, and the independent variable of the power consumption model is the M-dimension principal component data.
As a possible implementation, the distortion data in the acquired power consumption influence history data is filtered according to the content provided in fig. 4:
The setting step length may be set according to an actual application scenario, and is not limited herein.
And aiming at each dimension in the N dimensions, carrying out a variance homogeneity test, namely an F test, on the dimension power consumption influence historical data of all the second network elements in each sub-time period and the dimension power consumption influence historical data of all the second network elements in the second time period.
Wherein, the formula of the homogeneity test of the variance is as follows:
wherein the content of the first and second substances,
wherein v represents any sub-period, q represents any dimension, and YjRepresents j data in the q-dimension power consumption influence historical data of all the second network elements in the sub-time period v,
an average value, n, of q-dimensional power consumption impact history data representing all second network elements within the sub-period vvqRepresenting the total number of q-dimension power consumption influence historical data of all second network elements in the sub-period v, YrThe r-th data in the q-dimension power consumption impact history data of all the second network elements in the second time period,
an average value, m, of q-dimensional power consumption impact history data representing all second network elements in the second time periodqRepresenting the total number of q-dimensional power consumption impact historical data of all second network elements in a second time period, FvqAnd the q-dimension power consumption influence historical data of all the second network elements in the sub-time period v and the q-dimension power consumption influence historical data of all the second network elements in the second time period are represented as the same variance.
When F is not equal to 1, determining that the variance of the dimension power consumption influence history data of all the second network elements in any sub-period is different from the variance of the dimension power consumption influence history data of all the second network elements in a second period, and at this time, determining the dimension power consumption influence history data of all the second network elements in any sub-period as distortion data. The dimension power consumption influence history data in the sub-time period with the same variance as the dimension power consumption influence history data in the second time period can be determined as undistorted data, and the undistorted data is reserved. Further distortion data detection may also be performed on the dimension power consumption impact history data in a sub-period of time that has the same variance as the dimension power consumption impact history data in the second period of time.
According to the embodiment of the invention, the data is subjected to the homogeneity test of the variance to obtain the distortion data, so that the filtering of the distortion data is realized.
As an optional implementation manner, according to the content provided in fig. 5, further distortion data detection is performed on the dimension power consumption influence history data in each sub-time period having the same variance as the dimension power consumption influence history data in the second time period:
Wherein, a t-test is performed to check whether the difference between the average value of the values of the dimension power consumption influence history data in the sub-period and the average value of the values of the dimension power consumption influence history data in the second period is significant.
The single population t-test formula is:
where v represents any sub-period, q represents any dimension,
represents an average of the q-dimensional power consumption impact history data of all the second network elements within the sub-period v,
representing an average value, sigma, of the q-dimensional power consumption impact history data of all second network elements in the second time periodvqAnd the standard deviation, n, of q-dimension power consumption influence historical data of all second network elements in the sub-time period v is representedvqRepresenting the total number t of q-dimension power consumption influence historical data of all second network elements in the sub-time period vvqIs the dispersion statistic.
In specific implementation, if the single-population t-test result is not within the preset range, it indicates that the deviation between the dimension power consumption influence historical data in the sub-time period and the dimension power consumption influence historical data in the second time period is large, and at this time, the dimension power consumption influence historical data in the sub-time period is determined as distortion data. If the single-population t test result is within a preset range, the deviation between the dimension power consumption influence historical data in the sub-time period and the dimension power consumption influence historical data in the second time period is small, at the moment, the dimension power consumption influence historical data in the sub-time period is determined to be undistorted data, and the undistorted data is reserved.
As a possible implementation manner, if the power consumption influence data of the first network element in the first time period is N-dimensional power consumption influence data, the theoretical power consumption of the first network element in the first time period is determined according to the content provided in fig. 6:
In the embodiment of the present invention, when the theoretical power consumption of the first network element in the first time period is calculated by using the power consumption model, the N-dimensional power consumption influence data of the first network element in the first time period needs to be reduced to M-dimensional principal component data, so as to meet the requirement of the power consumption model on the input parameters.
Example two
An embodiment of the present invention provides a device for determining power consumption of a network element, as shown in fig. 7, including:
a first determining module 701, configured to determine, according to power consumption influence data of the first network element in a specified area in a first time period, theoretical power consumption of the first network element in the first time period by using a power consumption model obtained through pre-training;
a second determining module 702, configured to determine, according to the theoretical power consumption and a standard deviation of stored historical power consumption of all second network elements in the specified area in a second time period, a lowest power consumption and a highest power consumption of the first network element in the first time period, where a smart meter is disposed on the second network element.
Optionally, the apparatus for determining power consumption of a network element provided in the embodiment of the present invention further includes:
a training module 703, configured to train to obtain the power consumption model in the following manner:
acquiring N-dimensional power consumption influence historical data of each second network element in a second time period;
filtering distortion data in the acquired power consumption influence historical data to obtain N-dimension filtered power consumption influence historical data of each second network element;
for each second network element, performing dimensionality reduction on the filtered N-dimensional power consumption influence historical data of the second network element by using a principal component analysis method to obtain M-dimensional principal component data corresponding to the second network element, wherein N is an integer greater than 1, M is an integer greater than zero, and M is smaller than N;
and taking the M-dimension principal component data corresponding to each second network element as an independent variable, taking the power consumption of the corresponding second network element in a second time period as a dependent variable, and performing power consumption function fitting to obtain the power consumption model.
Optionally, the training module is specifically configured to filter distortion data in the acquired power consumption influence history data in the following manner:
dividing the second time period into a plurality of sub-time periods according to a set step length;
for each dimension in the N dimensions, carrying out a variance homogeneity test on the dimension power consumption influence historical data in each sub-time period and the dimension power consumption influence historical data in a second time period;
and determining the dimension power consumption influence historical data in the sub-time period with the variance different from that of the dimension power consumption influence historical data in the second time period as distortion data, and discarding the distortion data.
Optionally, the training module is further configured to:
aiming at the dimension power consumption influence historical data in each sub-time period with the same variance as the dimension power consumption influence historical data in a second time period, carrying out single-population t test on the dimension power consumption influence historical data in the sub-time period and the dimension power consumption influence historical data in the second time period;
and if the single-population t test result is not in the preset range, determining the dimension power consumption influence historical data in the sub-time period as distortion data, and discarding the distortion data.
Optionally, the power consumption influence data of the first network element in the first time period is N-dimensional power consumption influence data, and the first determining module is specifically configured to:
performing dimensionality reduction processing on N-dimensional power consumption influence data of a first network element in a first time period by using the principal component analysis method to obtain M-dimensional principal component data corresponding to the first network element;
inputting M-dimension principal component data corresponding to the first network element into the power consumption model to obtain the output of the power consumption model;
and determining the output of the power consumption model as the theoretical power consumption of the first network element in the first time period.
Optionally, the second determining module is specifically configured to:
determining the product of the standard deviation and a preset constant;
taking an absolute value of a difference value between the theoretical power consumption and the product as a lowest power consumption of the first network element in the first time period;
and taking the sum of the theoretical power consumption and the product as the highest power consumption of the first network element in the first time period.
EXAMPLE III
The embodiment of the invention provides a nonvolatile computer storage medium, wherein the computer storage medium stores an executable program, and the executable program is executed by a processor to realize the steps of the method for determining the power consumption of any network element provided by the first embodiment.
Example four
An embodiment of the present invention provides a computing device, configured to execute the method for determining power consumption of any network element in the first embodiment, as shown in fig. 8, which is a schematic diagram of a hardware structure of the computing device in the fourth embodiment of the present invention, where the computing device may specifically be a desktop computer, a portable computer, a smart phone, a tablet computer, and the like. The computing device may include a memory 801, a processor 802 and a computer program stored on the memory, the processor implementing the steps of the method for determining power consumption of any network element in the first embodiment when executing the program. Memory 801 may include Read Only Memory (ROM) and Random Access Memory (RAM), among other things, and provides processor 802 with program instructions and data stored in memory 801.
Further, the computing apparatus according to the fourth embodiment of the present invention may further include an input device 803, an output device 804, and the like. The input device 803 may include a keyboard, mouse, touch screen, etc.; the output device 804 may include a Display apparatus such as a Liquid Crystal Display (LCD), a Cathode Ray Tube (CRT), and the like. The memory 801, the processor 802, the input device 803, and the output device 804 may be connected by a bus or other means, and are exemplified by a bus in fig. 8.
The processor 802 calls the program instructions stored in the memory 801 and executes the method for determining the power consumption of the network element according to the first embodiment according to the obtained program instructions.
The method, the device, the storage medium and the computing equipment for determining the power consumption of the network element provided by the embodiment of the invention have the following beneficial effects:
the theoretical power consumption of the network element is determined by using the power consumption model obtained by pre-training and the power consumption influence data of the first network element, and the highest power consumption and the lowest power consumption of the first network element in a certain time period are determined according to the theoretical power consumption and the historical power consumption of the second network element provided with the intelligent electric meter, so that the power consumption range of the network element not provided with the intelligent electric meter in the certain time period can be determined without manual participation.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all such alterations and modifications as fall within the scope of the invention.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (12)
1. A method for determining power consumption of a network element, comprising:
according to power consumption influence data of a first network element in a specified area in a first time period, determining theoretical power consumption of the first network element in the first time period by using a power consumption model obtained through pre-training, wherein the power consumption model is obtained through training in the following mode: acquiring N-dimensional power consumption influence historical data of each second network element in a second time period; filtering distortion data in the acquired power consumption influence historical data to obtain N-dimension filtered power consumption influence historical data of each second network element; for each second network element, performing dimensionality reduction on the filtered N-dimensional power consumption influence historical data of the second network element by using a principal component analysis method to obtain M-dimensional principal component data corresponding to the second network element, wherein N is an integer greater than 1, M is an integer greater than zero, and M is smaller than N; taking the M-dimension principal component data corresponding to each second network element as an independent variable, taking the power consumption of the corresponding second network element in a second time period as a dependent variable, and performing power consumption function fitting to obtain the power consumption model;
and determining the lowest power consumption and the highest power consumption of the first network element in the first time period according to the theoretical power consumption and the stored standard deviation of the historical power consumption of all the second network elements in the specified area in the second time period, wherein the second network elements are provided with intelligent electric meters.
2. The method of claim 1, wherein filtering distortion data in the obtained power consumption impact history data specifically comprises:
dividing the second time period into a plurality of sub-time periods according to a set step length;
for each dimension in the N dimensions, carrying out a variance homogeneity test on the dimension power consumption influence historical data in each sub-time period and the dimension power consumption influence historical data in a second time period;
and determining the dimension power consumption influence historical data in the sub-time period with the variance different from that of the dimension power consumption influence historical data in the second time period as distortion data, and discarding the distortion data.
3. The method of claim 2, further comprising:
aiming at the dimension power consumption influence historical data in each sub-time period with the same variance as the dimension power consumption influence historical data in a second time period, carrying out single-population t test on the dimension power consumption influence historical data in the sub-time period and the dimension power consumption influence historical data in the second time period;
and if the single-population t test result is not in the preset range, determining the dimension power consumption influence historical data in the sub-time period as distortion data, and discarding the distortion data.
4. The method according to any one of claims 1 to 3, wherein if the power consumption impact data of the first network element in the first time period is N-dimensional power consumption impact data, determining the theoretical power consumption of the first network element in the first time period specifically includes:
performing dimensionality reduction processing on N-dimensional power consumption influence data of a first network element in a first time period by using the principal component analysis method to obtain M-dimensional principal component data corresponding to the first network element;
inputting M-dimension principal component data corresponding to the first network element into the power consumption model to obtain the output of the power consumption model;
and determining the output of the power consumption model as the theoretical power consumption of the first network element in the first time period.
5. The method of claim 1, wherein determining the lowest power consumption and the highest power consumption of the first network element in the first time period comprises:
determining the product of the standard deviation and a preset constant;
taking an absolute value of a difference value between the theoretical power consumption and the product as a lowest power consumption of the first network element in the first time period;
and taking the sum of the theoretical power consumption and the product as the highest power consumption of the first network element in the first time period.
6. A network element power consumption determination apparatus, comprising:
the first determining module is used for determining theoretical power consumption of a first network element in a first time period by using a power consumption model obtained by pre-training according to power consumption influence data of the first network element in a specified area in the first time period;
a second determining module, configured to determine, according to the theoretical power consumption and a standard deviation of stored historical power consumption of all second network elements in the specified area in a second time period, a lowest power consumption and a highest power consumption of the first network element in the first time period, where an intelligent electric meter is arranged on the second network element;
the device, still include:
the training module is used for training to obtain the power consumption model in the following way: acquiring N-dimensional power consumption influence historical data of each second network element in a second time period; filtering distortion data in the acquired power consumption influence historical data to obtain N-dimension filtered power consumption influence historical data of each second network element; for each second network element, performing dimensionality reduction on the filtered N-dimensional power consumption influence historical data of the second network element by using a principal component analysis method to obtain M-dimensional principal component data corresponding to the second network element, wherein N is an integer greater than 1, M is an integer greater than zero, and M is smaller than N; and taking the M-dimension principal component data corresponding to each second network element as an independent variable, taking the power consumption of the corresponding second network element in a second time period as a dependent variable, and performing power consumption function fitting to obtain the power consumption model.
7. The apparatus of claim 6, wherein the training module is specifically configured to filter distortion data in the obtained power consumption impact history data by:
dividing the second time period into a plurality of sub-time periods according to a set step length;
for each dimension in the N dimensions, carrying out a variance homogeneity test on the dimension power consumption influence historical data in each sub-time period and the dimension power consumption influence historical data in a second time period;
and determining the dimension power consumption influence historical data in the sub-time period with the variance different from that of the dimension power consumption influence historical data in the second time period as distortion data, and discarding the distortion data.
8. The apparatus of claim 7, wherein the training module is further to:
aiming at the dimension power consumption influence historical data in each sub-time period with the same variance as the dimension power consumption influence historical data in a second time period, carrying out single-population t test on the dimension power consumption influence historical data in the sub-time period and the dimension power consumption influence historical data in the second time period;
and if the single-population t test result is not in the preset range, determining the dimension power consumption influence historical data in the sub-time period as distortion data, and discarding the distortion data.
9. The apparatus according to any one of claims 6 to 8, wherein the power consumption impact data of the first network element in the first time period is N-dimensional power consumption impact data, and the first determining module is specifically configured to:
performing dimensionality reduction processing on N-dimensional power consumption influence data of a first network element in a first time period by using the principal component analysis method to obtain M-dimensional principal component data corresponding to the first network element;
inputting M-dimension principal component data corresponding to the first network element into the power consumption model to obtain the output of the power consumption model;
and determining the output of the power consumption model as the theoretical power consumption of the first network element in the first time period.
10. The apparatus of claim 6, wherein the second determining module is specifically configured to:
determining the product of the standard deviation and a preset constant;
taking an absolute value of a difference value between the theoretical power consumption and the product as a lowest power consumption of the first network element in the first time period;
and taking the sum of the theoretical power consumption and the product as the highest power consumption of the first network element in the first time period.
11. A non-transitory computer storage medium storing an executable program for execution by a processor to perform the steps of the method of any one of claims 1 to 5.
12. A computing device comprising a memory, a processor and a computer program stored on the memory, the processor implementing the steps of the method of any one of claims 1 to 5 when executing the program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710552179.5A CN109214637B (en) | 2017-07-07 | 2017-07-07 | Network element power consumption determination method and device, storage medium and computing equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710552179.5A CN109214637B (en) | 2017-07-07 | 2017-07-07 | Network element power consumption determination method and device, storage medium and computing equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109214637A CN109214637A (en) | 2019-01-15 |
| CN109214637B true CN109214637B (en) | 2020-12-08 |
Family
ID=64991148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710552179.5A Active CN109214637B (en) | 2017-07-07 | 2017-07-07 | Network element power consumption determination method and device, storage medium and computing equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214637B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930356A (en) * | 2012-11-16 | 2013-02-13 | 广东电网公司电力调度控制中心 | Short-term load forecast method based on meteorological factor sensitivity |
| CN103258069A (en) * | 2012-11-30 | 2013-08-21 | 武汉华中电力电网技术有限公司 | Forecasting method for power demand of iron and steel industry |
| CN103295075A (en) * | 2013-04-01 | 2013-09-11 | 沈阳航空航天大学 | Ultra-short-term power load forecasting and early warning method |
| CN104123617A (en) * | 2014-07-25 | 2014-10-29 | 国家电网公司 | Power load forecasting method |
| CN104537438A (en) * | 2014-12-26 | 2015-04-22 | 国家电网公司 | Forecast and monitoring method for peak-hour power usage |
| CN104573858A (en) * | 2014-12-26 | 2015-04-29 | 国家电网公司 | Prediction, regulation and control method for electric network loads |
| CN104599055A (en) * | 2015-01-04 | 2015-05-06 | 湘潭大学 | Power load demand management method for iron and steel enterprises |
| CN104992246A (en) * | 2015-07-09 | 2015-10-21 | 华南理工大学 | Improved-least-square-method-based prediction method of load electric quantity for transformer substation |
| CN105825294A (en) * | 2016-03-10 | 2016-08-03 | 国家电网公司 | Meteorological-factor-based grid power load prediction method and system |
| CN106570581A (en) * | 2016-10-26 | 2017-04-19 | 东北电力大学 | Attribute association based load prediction system and method in energy Internet environment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9361273B2 (en) * | 2011-07-21 | 2016-06-07 | Sap Se | Context-aware parameter estimation for forecast models |
| US9569804B2 (en) * | 2012-08-27 | 2017-02-14 | Gridium, Inc. | Systems and methods for energy consumption and energy demand management |
| US9576327B2 (en) * | 2013-06-06 | 2017-02-21 | International Business Machines Corporation | Managing time-substitutable electricity usage using dynamic controls |
-
2017
- 2017-07-07 CN CN201710552179.5A patent/CN109214637B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102930356A (en) * | 2012-11-16 | 2013-02-13 | 广东电网公司电力调度控制中心 | Short-term load forecast method based on meteorological factor sensitivity |
| CN103258069A (en) * | 2012-11-30 | 2013-08-21 | 武汉华中电力电网技术有限公司 | Forecasting method for power demand of iron and steel industry |
| CN103295075A (en) * | 2013-04-01 | 2013-09-11 | 沈阳航空航天大学 | Ultra-short-term power load forecasting and early warning method |
| CN104123617A (en) * | 2014-07-25 | 2014-10-29 | 国家电网公司 | Power load forecasting method |
| CN104537438A (en) * | 2014-12-26 | 2015-04-22 | 国家电网公司 | Forecast and monitoring method for peak-hour power usage |
| CN104573858A (en) * | 2014-12-26 | 2015-04-29 | 国家电网公司 | Prediction, regulation and control method for electric network loads |
| CN104599055A (en) * | 2015-01-04 | 2015-05-06 | 湘潭大学 | Power load demand management method for iron and steel enterprises |
| CN104992246A (en) * | 2015-07-09 | 2015-10-21 | 华南理工大学 | Improved-least-square-method-based prediction method of load electric quantity for transformer substation |
| CN105825294A (en) * | 2016-03-10 | 2016-08-03 | 国家电网公司 | Meteorological-factor-based grid power load prediction method and system |
| CN106570581A (en) * | 2016-10-26 | 2017-04-19 | 东北电力大学 | Attribute association based load prediction system and method in energy Internet environment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109214637A (en) | 2019-01-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109726364B (en) | Power consumption abnormity detection method, device, terminal and computer readable storage medium | |
| CN110147367B (en) | Temperature missing data filling method and system and electronic equipment | |
| CN103750552B (en) | A kind of intelligent sampling method and the application controlled at quality cigarette thereof | |
| CN104123519A (en) | System for automatically detecting electronic products through two-dimension codes and method thereof | |
| CN111738348B (en) | Power data anomaly detection method and device | |
| CN104243815A (en) | Focusing method and electronic equipment | |
| CN110751416A (en) | Method, device and equipment for predicting water consumption | |
| CN112527601A (en) | Monitoring early warning method and device | |
| CN104954528A (en) | Detection method and apparatus of electricity consumption information of terminal equipment | |
| CN113094325B (en) | Device deployment method, device, computer system and computer readable storage medium | |
| CN110826859A (en) | Method and system for remotely identifying electricity consumption property of user based on daily electricity quantity | |
| CN109214637B (en) | Network element power consumption determination method and device, storage medium and computing equipment | |
| CN104933178B (en) | Official website determines method and system and the sort method of official website | |
| WO2024066720A1 (en) | Indicator threshold determination method and apparatus, storage medium, and electronic apparatus | |
| CN113238911B (en) | Alarm processing method and device | |
| CN103631232A (en) | Data monitoring control method and data monitoring control device | |
| CN115453447A (en) | Online detection method for out-of-tolerance electric meter based on suspected electric meter stepwise compensation rejection | |
| CN115186751A (en) | CVT metering error prediction method and device based on s transformation and storage medium | |
| CN106856417B (en) | Method and device for detecting antenna feeder installation problem | |
| CN112995650B (en) | Method and device for detecting video continuity of camera | |
| CN109918353B (en) | Method for automatically processing information and terminal equipment | |
| CN111354096A (en) | Intelligent attendance checking method and device and electronic equipment | |
| CN110956091A (en) | Electric energy meter identification method and device, computer equipment and storage medium | |
| CN113127333A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN110888100A (en) | Single-phase intelligent electric energy meter online on-load detection system and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |